Application of Convolutional Long Short-Term Memory Neural Networks to Signals Collected from a Sensor Network for Autonomous Gas Source Localization in Outdoor Environments

Abstract

Convolutional Long Short-Term Memory Neural Networks (CNN-LSTM) are a variant of recurrent neural networks (RNN) that can extract spatial features in addition to classifying or making predictions from sequential data. In this paper, we analyzed the use of CNN-LSTM for gas source localization (GSL) in outdoor environments using time series data from a gas sensor network and anemometer. CNN-LSTM is used to estimate the location of a gas source despite the challenges created from inconsistent airflow and gas distribution in outdoor environments. To train CNN-LSTM for GSL, we used temporal data taken from a 5 × 6 metal oxide semiconductor (MOX) gas sensor array, spaced 1.5 m apart, and an anemometer placed in the center of the sensor array in an open area outdoors. The output of the CNN-LSTM is one of thirty cells approximating the location of a gas source. We show that by using CNN-LSTM, we were able to determine the location of a gas source from sequential data. In addition, we compared several artificial neural network (ANN) architectures as well as trained them without wind vector data to estimate the complexity of the task. We found that ANN is a promising prospect for GSL tasks.

A Deep Learning Framework for Driving Behavior Identification on In-Vehicle CAN-BUS Sensor Data

“…Furthermore, in most of the state-of-the-art works on CNN for activity recognition, 1D/2D convolution was employed in individual time series to capture local dependency along the temporal dimension of sensor signals [21,22]. The combination of CNN and LSTM had already offered state-of-the-art results in speech recognition, wearable activity recognition, online defect recognition of CO 2 welding, etc., where modeling temporal information was required [14,23,24,25,26]. This kind of architecture was able to capture time dependencies on features extracted by convolution operations.…”

“…Compared to the structure of DeepConvLSTM proposed in [14,23,24,25,26], we introduce an attention mechanism in [30], and redesign the convolutional and recurrent layer referring to [31,32]. As shown in Figure 5, the proposed model for driving behavior identification using in-vehicle CAN-BUS sensor data consists of an input layer, middle layers and a classifier layer.…”

k-NN and k-NN-ANN Combined Classifier to Assess MOX Gas Sensors Performances Affected by Drift Caused by Early Life Aging

“…Metal oxide semiconductor (MOX) gas sensors are characterized by high sensitivity, fast response, and low cost. Those characteristics make their application very promising in different fields, such as agri-food quality and safety [1][2][3][4][5], environmental monitoring [6][7][8], home security [9][10][11], and human health [12][13][14] among the most investigated. Although these features make MOX sensors one of the most promising technologies of recent years, their diffusion is limited due to some disadvantages.…”

Gas Leakage Source Detection for Li-Ion Batteries by Distributed Sensor Array

“…According to the International Union of Pure and Applied Chemistry (IUPAC), the LoD is defined as the “smallest measure that can be detected with reasonable certainty for a given analytical procedure” [6]. As a statistical measure based on the standard deviation of a linear static output characteristic, the LoD could be extended for dynamic sensor response uncertainty [7] and multisensory measuring system calibration [8]. Numerical reconstruction methods for source location are well known approaches [7,8,9,10] but the computational complexity of inverse source reconstruction algorithms could be inappropriate for onboard monitoring system controllers [1].…”

“…As a statistical measure based on the standard deviation of a linear static output characteristic, the LoD could be extended for dynamic sensor response uncertainty [7] and multisensory measuring system calibration [8]. Numerical reconstruction methods for source location are well known approaches [7,8,9,10] but the computational complexity of inverse source reconstruction algorithms could be inappropriate for onboard monitoring system controllers [1]. Some reduced computational complexity methods, like artificial neural networks, are proposed in [8].…”